Method and Apparatus for Restoring Image

2. The image restoration method of claim 1, wherein the plurality of input images of the plurality of pieces of input image information are captured by using lenses located in different positions.

3. The image restoration method of claim 2, wherein the generating the plurality of pieces of warped image information comprises generating, with respect to each of the plurality of disparities, a plurality of warped images, as the plurality of pieces of warped image information, by warping each of the plurality of input images to a pixel coordinate system corresponding to a target image based on a depth corresponding to each of the plurality of disparities.

4. The image restoration method of claim 3, wherein the generating the plurality of warped images comprises generating a warped image by warping all of pixels in a first input image, among the plurality of input images, to the pixel coordinate system corresponding to the target image based on a single depth corresponding to a first disparity among the plurality of disparities.

5. The image restoration method of claim 3, wherein a disparity is set for an input image with respect to the target image, and the depth corresponding to the disparity is based on the disparity and a gap between sensing units that capture the target image and the input image.

6. The image restoration method of claim 3, wherein the generating the output image comprises generating the output image by providing, as an input to the image restoration model, data obtained by concatenating the plurality of input images and the plurality of warped images corresponding to each of the plurality of disparities.

7. The image restoration method of claim 1, wherein the plurality of pieces of input image information comprises a plurality of input feature maps extracted from the plurality of input images by using a feature extraction model.

8. The image restoration method of claim 7, wherein the generating the plurality of pieces of warped image information comprises generating, with respect to each of the plurality of disparities, a plurality of warped feature maps, as the plurality of pieces of warped image information, by warping each of the plurality of input feature maps to a pixel coordinate system corresponding to a target image based on a depth corresponding to each of the plurality of disparities.

9. The image restoration method of claim 8, wherein the generating the output image comprises generating the output image by providing, as an input to the image restoration model, data obtained by concatenating the plurality of input feature maps and the plurality of warped feature maps corresponding to each of the plurality of disparities.

10. The image restoration method of claim 1, wherein the image restoration model is a neural network comprising at least one convolution layer configured to apply a convolution filtering to input data.

12. The image restoration method of claim 11, wherein the plurality of disparities are a finite number of disparities.

13. The image restoration method of claim 1, wherein the generating the output image comprises generating the output image without sensing a depth to the target point corresponding to an individual pixel of an input image.

15. The image restoration method of claim 1, wherein a resolution of the output image is higher than a resolution of each of the plurality of pieces of input image information.

16. The image restoration method of claim 1, wherein the plurality of pieces of input image information comprise a multi-lens image captured by an image sensor including a multi-lens array, the multi-lens image including the plurality of input images.

17. The image restoration method of claim 1, wherein the plurality of input images of the plurality of pieces of input image information are respectively captured by a plurality of image sensors.

18. A non-transitory computer-readable storage medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform the method of claim 1.

21. The image restoration apparatus of claim 20, wherein a resolution of the output image is higher than a resolution corresponding to each of the plurality of pieces of input information.

22. The image restoration apparatus of claim 20, wherein the processor is further configured to generate, with respect to each of the plurality of disparities, the plurality of pieces of warped information by warping each of the plurality of pieces of input information to a pixel coordinate system corresponding to a target image based on a depth corresponding to each of the plurality of disparities.

23. The image restoration apparatus of claim 22, wherein the processor is further configured to generate a piece of warped information by warping all of pixels corresponding to a piece of input information, among the plurality of pieces of input information, to the pixel coordinate system corresponding to the target image based on a single depth corresponding to a first disparity among the plurality of disparities.

24. The image restoration apparatus of claim 22, wherein the processor is further configured to generate the output image by providing, as an input to the image restoration model, data obtained by concatenating the plurality of pieces of input information and the plurality of pieces of warped information corresponding to each of the plurality of disparities.

25. The image restoration apparatus of claim 20, wherein the processor is further configured to extract, as the plurality of pieces of input information, a plurality of input feature maps from the plurality of input images, by using a feature extraction model.

26. The image restoration apparatus of claim 25, wherein the processor is further configured to generate, with respect to each of the plurality of disparities, a plurality of warped feature maps, as the plurality of pieces of warped information, by warping each of the plurality of input feature maps to a pixel coordinate system corresponding to a target image based on a depth corresponding to each of the plurality of disparities.

27. The image restoration apparatus of claim 26, wherein the processor is further configured to generate the output image by providing, as an input to the image restoration model, data obtained by concatenating the plurality of input feature maps and the plurality of warped feature maps corresponding to each of the plurality of disparities.